Transfer Learning Gaussian Anomaly Detection by Fine-tuning Representations
arXiv:2108.04116 · doi:10.5220/0011063900003209
Abstract
Current state-of-the-art anomaly detection (AD) methods exploit the powerful representations yielded by large-scale ImageNet training. However, catastrophic forgetting prevents the successful fine-tuning of pre-trained representations on new datasets in the semi-supervised setting, and representations are therefore commonly fixed. In our work, we propose a new method to overcome catastrophic forgetting and thus successfully fine-tune pre-trained representations for AD in the transfer learning setting. Specifically, we induce a multivariate Gaussian distribution for the normal class based on the linkage between generative and discriminative modeling, and use the Mahalanobis distance of normal images to the estimated distribution as training objective. We additionally propose to use augmentations commonly employed for vicinal risk minimization in a validation scheme to detect onset of catastrophic forgetting. Extensive evaluations on the public MVTec dataset reveal that a new state of the art is achieved by our method in the AD task while simultaneously achieving anomaly segmentation performance comparable to prior state of the art. Further, ablation studies demonstrate the importance of the induced Gaussian distribution as well as the robustness of the proposed fine-tuning scheme with respect to the choice of augmentations.
arXiv commentCamera ready for IMPROVE22 + additional typo fixes
References in corpus (19)
- Adam: A Method for Stochastic Optimization
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Overcoming catastrophic forgetting in neural networks
- Improved Regularization of Convolutional Neural Networks with Cutout
- Variational Inference with Normalizing Flows
- A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
- Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings
- AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
- Deep Anomaly Detection Using Geometric Transformations
- Sub-Image Anomaly Detection with Deep Pyramid Correspondences
- Intriguing Properties of Vision Transformers
- The Origins and Prevalence of Texture Bias in Convolutional Neural Networks
- Explainable Deep One-Class Classification
- Attribute Restoration Framework for Anomaly Detection
- Why is the Mahalanobis Distance Effective for Anomaly Detection?
- An Analysis of Pre-Training on Object Detection
- Understanding the Effect of Bias in Deep Anomaly Detection